llvm/llvm/test/CodeGen/AArch64/machine-combiner-fmul-dup.mir

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -run-pass=machine-combiner -o - -simplify-mir -mtriple=aarch64-unknown-linux-gnu -mattr=+fullfp16 -verify-machineinstrs %s | FileCheck %s
--- |
  ; ModuleID = 'lit.ll'
  source_filename = "lit.ll"
  target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
  target triple = "aarch64-unknown-linux-gnu"

  define void @indexed_2s(<2 x float> %shuf, <2 x float> %mu, <2 x float> %ad, ptr %ret) #0 {
  entry:
    %shuffle = shufflevector <2 x float> %shuf, <2 x float> undef, <2 x i32> zeroinitializer
    br label %for.cond

  for.cond:                                         ; preds = %for.cond, %entry
    %mul = fmul <2 x float> %mu, %shuffle
    %add = fadd <2 x float> %mul, %ad
    store <2 x float> %add, ptr %ret, align 16
    br label %for.cond
  }

  define void @indexed_2s_rev(<2 x float> %shuf, <2 x float> %mu, <2 x float> %ad, ptr %ret) #0 {
  entry:
    %shuffle = shufflevector <2 x float> %shuf, <2 x float> undef, <2 x i32> zeroinitializer
    br label %for.cond

  for.cond:                                         ; preds = %for.cond, %entry
    %mul = fmul <2 x float> %shuffle, %mu
    %add = fadd <2 x float> %mul, %ad
    store <2 x float> %add, ptr %ret, align 16
    br label %for.cond
  }

  define void @indexed_2d(<2 x double> %shuf, <2 x double> %mu, <2 x double> %ad, ptr %ret) #0 {
  entry:
    %shuffle = shufflevector <2 x double> %shuf, <2 x double> undef, <2 x i32> zeroinitializer
    br label %for.cond

  for.cond:                                         ; preds = %for.cond, %entry
    %mul = fmul <2 x double> %mu, %shuffle
    %add = fadd <2 x double> %mul, %ad
    store <2 x double> %add, ptr %ret, align 16
    br label %for.cond
  }

  define void @indexed_4s(<4 x float> %shuf, <4 x float> %mu, <4 x float> %ad, ptr %ret) #0 {
  entry:
    %shuffle = shufflevector <4 x float> %shuf, <4 x float> undef, <4 x i32> zeroinitializer
    br label %for.cond

  for.cond:                                         ; preds = %for.cond, %entry
    %mul = fmul <4 x float> %mu, %shuffle
    %add = fadd <4 x float> %mul, %ad
    store <4 x float> %add, ptr %ret, align 16
    br label %for.cond
  }

  define void @indexed_4h(<4 x half> %shuf, <4 x half> %mu, <4 x half> %ad, ptr %ret) #0 {
  entry:
    %shuffle = shufflevector <4 x half> %shuf, <4 x half> undef, <4 x i32> zeroinitializer
    br label %for.cond

  for.cond:
    %mul = fmul <4 x half> %mu, %shuffle
    %add = fadd <4 x half> %mul, %ad
    store <4 x half> %add, ptr %ret, align 16
    br label %for.cond
  }

  define void @indexed_8h(<8 x half> %shuf, <8 x half> %mu, <8 x half> %ad, ptr %ret) #0 {
  entry:
    %shuffle = shufflevector <8 x half> %shuf, <8 x half> undef, <8 x i32> zeroinitializer
    br label %for.cond

  for.cond:
    %mul = fmul <8 x half> %mu, %shuffle
    %add = fadd <8 x half> %mul, %ad
    store <8 x half> %add, ptr %ret, align 16
    br label %for.cond
  }

  define void @kill_state(<2 x float> %shuf, <2 x float> %mu, <2 x float> %ad,
                          ptr %ret, ptr %ret2, float %f) #0 {
  entry:
    %zero_elem = extractelement <2 x float> %shuf, i32 0
    %ins = insertelement <2 x float> undef, float %zero_elem, i32 0
    %shuffle = shufflevector <2 x float> %ins, <2 x float> undef, <2 x i32> zeroinitializer
    %ins2 = insertelement <2 x float> %ins, float %f, i32 1
    store <2 x float> %ins2, ptr %ret2, align 8
    br label %for.cond

  for.cond:                                         ; preds = %for.cond, %entry
    %mul = fmul <2 x float> %mu, %shuffle
    %add = fadd <2 x float> %mul, %ad
    store <2 x float> %add, ptr %ret, align 16
    br label %for.cond
  }

  define void @extracopy(<2 x float> %shuf, <2 x float> %mu, <2 x float> %ad, ptr %ret) #0 {
    unreachable
  }

  attributes #0 = { "target-cpu"="cortex-a57" }

...
---
name:            indexed_2s
alignment:       16
tracksRegLiveness: true
registers:
  - { id: 0, class: fpr64 }
  - { id: 1, class: fpr64 }
  - { id: 2, class: fpr64 }
  - { id: 3, class: fpr64 }
  - { id: 4, class: gpr64common }
  - { id: 5, class: fpr64 }
  - { id: 6, class: fpr64 }
  - { id: 7, class: fpr128 }
  - { id: 8, class: fpr128 }
  - { id: 9, class: fpr64 }
  - { id: 10, class: fpr64 }
liveins:
  - { reg: '$d0', virtual-reg: '%1' }
  - { reg: '$d1', virtual-reg: '%2' }
  - { reg: '$d2', virtual-reg: '%3' }
  - { reg: '$x0', virtual-reg: '%4' }
frameInfo:
  maxAlignment:    1
  maxCallFrameSize: 0
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: indexed_2s
  ; CHECK: bb.0.entry:
  ; CHECK-NEXT:   liveins: $d0, $d1, $d2, $x0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:gpr64common = COPY $x0
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:fpr64 = COPY $d2
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:fpr64 = COPY $d1
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:fpr64 = COPY $d0
  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:fpr128 = IMPLICIT_DEF
  ; CHECK-NEXT:   [[INSERT_SUBREG:%[0-9]+]]:fpr128 = INSERT_SUBREG [[DEF]], [[COPY3]], %subreg.dsub
  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:fpr64 = COPY [[COPY1]]
  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:fpr64 = COPY [[COPY2]]
  ; CHECK-NEXT:   [[DUPv2i32lane:%[0-9]+]]:fpr64 = DUPv2i32lane [[INSERT_SUBREG]], 0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1.for.cond:
  ; CHECK-NEXT:   [[FMULv2i32_indexed:%[0-9]+]]:fpr64 = FMULv2i32_indexed [[COPY5]], [[INSERT_SUBREG]], 0, implicit $fpcr
  ; CHECK-NEXT:   [[FADDv2f32_:%[0-9]+]]:fpr64 = FADDv2f32 killed [[FMULv2i32_indexed]], [[COPY4]], implicit $fpcr
  ; CHECK-NEXT:   STRDui killed [[FADDv2f32_]], [[COPY]], 0 :: (store (s64) into %ir.ret, align 16)
  ; CHECK-NEXT:   B %bb.1
  bb.0.entry:
    liveins: $d0, $d1, $d2, $x0

    %4:gpr64common = COPY $x0
    %3:fpr64 = COPY $d2
    %2:fpr64 = COPY $d1
    %1:fpr64 = COPY $d0
    %8:fpr128 = IMPLICIT_DEF
    %7:fpr128 = INSERT_SUBREG %8, %1, %subreg.dsub
    %6:fpr64 = COPY %3
    %5:fpr64 = COPY %2
    %0:fpr64 = DUPv2i32lane killed %7, 0

  bb.1.for.cond:
    %9:fpr64 = FMULv2f32 %5, %0, implicit $fpcr
    %10:fpr64 = FADDv2f32 killed %9, %6, implicit $fpcr
    STRDui killed %10, %4, 0 :: (store 8 into %ir.ret, align 16)
    B %bb.1

...
---
name:            indexed_2s_rev
alignment:       16
tracksRegLiveness: true
registers:
  - { id: 0, class: fpr64 }
  - { id: 1, class: fpr64 }
  - { id: 2, class: fpr64 }
  - { id: 3, class: fpr64 }
  - { id: 4, class: gpr64common }
  - { id: 5, class: fpr64 }
  - { id: 6, class: fpr64 }
  - { id: 7, class: fpr128 }
  - { id: 8, class: fpr128 }
  - { id: 9, class: fpr64 }
  - { id: 10, class: fpr64 }
liveins:
  - { reg: '$d0', virtual-reg: '%1' }
  - { reg: '$d1', virtual-reg: '%2' }
  - { reg: '$d2', virtual-reg: '%3' }
  - { reg: '$x0', virtual-reg: '%4' }
frameInfo:
  maxAlignment:    1
  maxCallFrameSize: 0
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: indexed_2s_rev
  ; CHECK: bb.0.entry:
  ; CHECK-NEXT:   liveins: $d0, $d1, $d2, $x0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:gpr64common = COPY $x0
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:fpr64 = COPY $d2
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:fpr64 = COPY $d1
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:fpr64 = COPY $d0
  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:fpr128 = IMPLICIT_DEF
  ; CHECK-NEXT:   [[INSERT_SUBREG:%[0-9]+]]:fpr128 = INSERT_SUBREG [[DEF]], [[COPY3]], %subreg.dsub
  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:fpr64 = COPY [[COPY1]]
  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:fpr64 = COPY [[COPY2]]
  ; CHECK-NEXT:   [[DUPv2i32lane:%[0-9]+]]:fpr64 = DUPv2i32lane [[INSERT_SUBREG]], 0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1.for.cond:
  ; CHECK-NEXT:   [[FMULv2i32_indexed:%[0-9]+]]:fpr64 = FMULv2i32_indexed [[COPY5]], [[INSERT_SUBREG]], 0, implicit $fpcr
  ; CHECK-NEXT:   [[FADDv2f32_:%[0-9]+]]:fpr64 = FADDv2f32 killed [[FMULv2i32_indexed]], [[COPY4]], implicit $fpcr
  ; CHECK-NEXT:   STRDui killed [[FADDv2f32_]], [[COPY]], 0 :: (store (s64) into %ir.ret, align 16)
  ; CHECK-NEXT:   B %bb.1
  bb.0.entry:
    liveins: $d0, $d1, $d2, $x0

    %4:gpr64common = COPY $x0
    %3:fpr64 = COPY $d2
    %2:fpr64 = COPY $d1
    %1:fpr64 = COPY $d0
    %8:fpr128 = IMPLICIT_DEF
    %7:fpr128 = INSERT_SUBREG %8, %1, %subreg.dsub
    %6:fpr64 = COPY %3
    %5:fpr64 = COPY %2
    %0:fpr64 = DUPv2i32lane killed %7, 0

  bb.1.for.cond:
    %9:fpr64 = FMULv2f32 %0, %5, implicit $fpcr
    %10:fpr64 = FADDv2f32 killed %9, %6, implicit $fpcr
    STRDui killed %10, %4, 0 :: (store 8 into %ir.ret, align 16)
    B %bb.1

...
---
name:            indexed_2d
alignment:       16
tracksRegLiveness: true
registers:
  - { id: 0, class: fpr128 }
  - { id: 1, class: fpr128 }
  - { id: 2, class: fpr128 }
  - { id: 3, class: fpr128 }
  - { id: 4, class: gpr64common }
  - { id: 5, class: fpr128 }
  - { id: 6, class: fpr128 }
  - { id: 7, class: fpr128 }
  - { id: 8, class: fpr128 }
liveins:
  - { reg: '$q0', virtual-reg: '%1' }
  - { reg: '$q1', virtual-reg: '%2' }
  - { reg: '$q2', virtual-reg: '%3' }
  - { reg: '$x0', virtual-reg: '%4' }
frameInfo:
  maxAlignment:    1
  maxCallFrameSize: 0
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: indexed_2d
  ; CHECK: bb.0.entry:
  ; CHECK-NEXT:   liveins: $q0, $q1, $q2, $x0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:gpr64common = COPY $x0
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:fpr128 = COPY $q2
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:fpr128 = COPY $q1
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:fpr128 = COPY $q0
  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:fpr128 = COPY [[COPY1]]
  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:fpr128 = COPY [[COPY2]]
  ; CHECK-NEXT:   [[DUPv2i64lane:%[0-9]+]]:fpr128 = DUPv2i64lane [[COPY3]], 0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1.for.cond:
  ; CHECK-NEXT:   [[FMULv2i64_indexed:%[0-9]+]]:fpr128 = FMULv2i64_indexed [[COPY5]], [[COPY3]], 0, implicit $fpcr
  ; CHECK-NEXT:   [[FADDv2f64_:%[0-9]+]]:fpr128 = FADDv2f64 killed [[FMULv2i64_indexed]], [[COPY4]], implicit $fpcr
  ; CHECK-NEXT:   STRQui killed [[FADDv2f64_]], [[COPY]], 0 :: (store (s128) into %ir.ret)
  ; CHECK-NEXT:   B %bb.1
  bb.0.entry:
    liveins: $q0, $q1, $q2, $x0

    %4:gpr64common = COPY $x0
    %3:fpr128 = COPY $q2
    %2:fpr128 = COPY $q1
    %1:fpr128 = COPY $q0
    %6:fpr128 = COPY %3
    %5:fpr128 = COPY %2
    %0:fpr128 = DUPv2i64lane %1, 0

  bb.1.for.cond:
    %7:fpr128 = FMULv2f64 %5, %0, implicit $fpcr
    %8:fpr128 = FADDv2f64 killed %7, %6, implicit $fpcr
    STRQui killed %8, %4, 0 :: (store 16 into %ir.ret)
    B %bb.1

...
---
name:            indexed_4s
alignment:       16
tracksRegLiveness: true
registers:
  - { id: 0, class: fpr128 }
  - { id: 1, class: fpr128 }
  - { id: 2, class: fpr128 }
  - { id: 3, class: fpr128 }
  - { id: 4, class: gpr64common }
  - { id: 5, class: fpr128 }
  - { id: 6, class: fpr128 }
  - { id: 7, class: fpr128 }
  - { id: 8, class: fpr128 }
liveins:
  - { reg: '$q0', virtual-reg: '%1' }
  - { reg: '$q1', virtual-reg: '%2' }
  - { reg: '$q2', virtual-reg: '%3' }
  - { reg: '$x0', virtual-reg: '%4' }
frameInfo:
  maxAlignment:    1
  maxCallFrameSize: 0
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: indexed_4s
  ; CHECK: bb.0.entry:
  ; CHECK-NEXT:   liveins: $q0, $q1, $q2, $x0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:gpr64common = COPY $x0
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:fpr128 = COPY $q2
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:fpr128 = COPY $q1
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:fpr128 = COPY $q0
  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:fpr128 = COPY [[COPY1]]
  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:fpr128 = COPY [[COPY2]]
  ; CHECK-NEXT:   [[DUPv4i32lane:%[0-9]+]]:fpr128 = DUPv4i32lane [[COPY3]], 0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1.for.cond:
  ; CHECK-NEXT:   [[FMULv4i32_indexed:%[0-9]+]]:fpr128 = FMULv4i32_indexed [[COPY5]], [[COPY3]], 0, implicit $fpcr
  ; CHECK-NEXT:   [[FADDv4f32_:%[0-9]+]]:fpr128 = FADDv4f32 killed [[FMULv4i32_indexed]], [[COPY4]], implicit $fpcr
  ; CHECK-NEXT:   STRQui killed [[FADDv4f32_]], [[COPY]], 0 :: (store (s128) into %ir.ret)
  ; CHECK-NEXT:   B %bb.1
  bb.0.entry:
    liveins: $q0, $q1, $q2, $x0

    %4:gpr64common = COPY $x0
    %3:fpr128 = COPY $q2
    %2:fpr128 = COPY $q1
    %1:fpr128 = COPY $q0
    %6:fpr128 = COPY %3
    %5:fpr128 = COPY %2
    %0:fpr128 = DUPv4i32lane %1, 0

  bb.1.for.cond:
    %7:fpr128 = FMULv4f32 %5, %0, implicit $fpcr
    %8:fpr128 = FADDv4f32 killed %7, %6, implicit $fpcr
    STRQui killed %8, %4, 0 :: (store 16 into %ir.ret)
    B %bb.1

...
---
name:            indexed_4h
alignment:       16
tracksRegLiveness: true
registers:
  - { id: 0, class: fpr64 }
  - { id: 1, class: fpr64 }
  - { id: 2, class: fpr64 }
  - { id: 3, class: fpr64 }
  - { id: 4, class: gpr64common }
  - { id: 5, class: fpr128 }
  - { id: 6, class: fpr128 }
  - { id: 7, class: fpr64 }
  - { id: 8, class: fpr64 }
liveins:
  - { reg: '$d0', virtual-reg: '%1' }
  - { reg: '$d1', virtual-reg: '%2' }
  - { reg: '$d2', virtual-reg: '%3' }
  - { reg: '$x0', virtual-reg: '%4' }
frameInfo:
  maxAlignment:    1
  maxCallFrameSize: 0
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: indexed_4h
  ; CHECK: bb.0.entry:
  ; CHECK-NEXT:   liveins: $d0, $d1, $d2, $x0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:gpr64common = COPY $x0
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:fpr64 = COPY $d2
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:fpr64 = COPY $d1
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:fpr64 = COPY $d0
  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:fpr128 = IMPLICIT_DEF
  ; CHECK-NEXT:   [[INSERT_SUBREG:%[0-9]+]]:fpr128_lo = INSERT_SUBREG [[DEF]], [[COPY3]], %subreg.dsub
  ; CHECK-NEXT:   [[DUPv4i16lane:%[0-9]+]]:fpr64 = DUPv4i16lane [[INSERT_SUBREG]], 0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1.for.cond:
  ; CHECK-NEXT:   [[FMULv4i16_indexed:%[0-9]+]]:fpr64 = FMULv4i16_indexed [[COPY2]], [[INSERT_SUBREG]], 0, implicit $fpcr
  ; CHECK-NEXT:   [[FADDv4f16_:%[0-9]+]]:fpr64 = FADDv4f16 killed [[FMULv4i16_indexed]], [[COPY1]], implicit $fpcr
  ; CHECK-NEXT:   STRDui killed [[FADDv4f16_]], [[COPY]], 0 :: (store (s64) into %ir.ret, align 16)
  ; CHECK-NEXT:   B %bb.1
  bb.0.entry:
    liveins: $d0, $d1, $d2, $x0

    %4:gpr64common = COPY $x0
    %3:fpr64 = COPY $d2
    %2:fpr64 = COPY $d1
    %1:fpr64 = COPY $d0
    %6:fpr128 = IMPLICIT_DEF
    %5:fpr128 = INSERT_SUBREG %6, %1, %subreg.dsub
    %0:fpr64 = DUPv4i16lane killed %5, 0

  bb.1.for.cond:
    %7:fpr64 = FMULv4f16 %2, %0, implicit $fpcr
    %8:fpr64 = FADDv4f16 killed %7, %3, implicit $fpcr
    STRDui killed %8, %4, 0 :: (store 8 into %ir.ret, align 16)
    B %bb.1

...
---
name:            indexed_8h
alignment:       16
tracksRegLiveness: true
registers:
  - { id: 0, class: fpr128 }
  - { id: 1, class: fpr128 }
  - { id: 2, class: fpr128 }
  - { id: 3, class: fpr128 }
  - { id: 4, class: gpr64common }
  - { id: 5, class: fpr128 }
  - { id: 6, class: fpr128 }
liveins:
  - { reg: '$q0', virtual-reg: '%1' }
  - { reg: '$q1', virtual-reg: '%2' }
  - { reg: '$q2', virtual-reg: '%3' }
  - { reg: '$x0', virtual-reg: '%4' }
frameInfo:
  maxAlignment:    1
  maxCallFrameSize: 0
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: indexed_8h
  ; CHECK: bb.0.entry:
  ; CHECK-NEXT:   liveins: $q0, $q1, $q2, $x0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:gpr64common = COPY $x0
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:fpr128 = COPY $q2
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:fpr128 = COPY $q1
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:fpr128_lo = COPY $q0
  ; CHECK-NEXT:   [[DUPv8i16lane:%[0-9]+]]:fpr128 = DUPv8i16lane [[COPY3]], 0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1.for.cond:
  ; CHECK-NEXT:   [[FMULv8i16_indexed:%[0-9]+]]:fpr128 = FMULv8i16_indexed [[COPY2]], [[COPY3]], 0, implicit $fpcr
  ; CHECK-NEXT:   [[FADDv8f16_:%[0-9]+]]:fpr128 = FADDv8f16 killed [[FMULv8i16_indexed]], [[COPY1]], implicit $fpcr
  ; CHECK-NEXT:   STRQui killed [[FADDv8f16_]], [[COPY]], 0 :: (store (s128) into %ir.ret)
  ; CHECK-NEXT:   B %bb.1
  bb.0.entry:
    liveins: $q0, $q1, $q2, $x0

    %4:gpr64common = COPY $x0
    %3:fpr128 = COPY $q2
    %2:fpr128 = COPY $q1
    %1:fpr128 = COPY $q0
    %0:fpr128 = DUPv8i16lane %1, 0

  bb.1.for.cond:
    %5:fpr128 = FMULv8f16 %2, %0, implicit $fpcr
    %6:fpr128 = FADDv8f16 killed %5, %3, implicit $fpcr
    STRQui killed %6, %4, 0 :: (store 16 into %ir.ret)
    B %bb.1

...
---
name:            kill_state
alignment:       16
tracksRegLiveness: true
registers:
  - { id: 0, class: fpr64 }
  - { id: 1, class: fpr64 }
  - { id: 2, class: fpr64 }
  - { id: 3, class: fpr64 }
  - { id: 4, class: gpr64common }
  - { id: 5, class: gpr64common }
  - { id: 6, class: fpr32 }
  - { id: 7, class: fpr64 }
  - { id: 8, class: fpr64 }
  - { id: 9, class: fpr128 }
  - { id: 10, class: fpr128 }
  - { id: 11, class: fpr128 }
  - { id: 12, class: fpr128 }
  - { id: 13, class: fpr128 }
  - { id: 14, class: fpr64 }
  - { id: 15, class: fpr64 }
  - { id: 16, class: fpr64 }
liveins:
  - { reg: '$d0', virtual-reg: '%1' }
  - { reg: '$d1', virtual-reg: '%2' }
  - { reg: '$d2', virtual-reg: '%3' }
  - { reg: '$x0', virtual-reg: '%4' }
  - { reg: '$x1', virtual-reg: '%5' }
  - { reg: '$s3', virtual-reg: '%6' }
frameInfo:
  maxAlignment:    1
  maxCallFrameSize: 0
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: kill_state
  ; CHECK: bb.0.entry:
  ; CHECK-NEXT:   liveins: $d0, $d1, $d2, $x0, $x1, $s3
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:fpr32 = COPY $s3
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:gpr64common = COPY $x1
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:gpr64common = COPY $x0
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:fpr64 = COPY $d2
  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:fpr64 = COPY $d1
  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:fpr64 = COPY $d0
  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:fpr128 = IMPLICIT_DEF
  ; CHECK-NEXT:   [[INSERT_SUBREG:%[0-9]+]]:fpr128 = INSERT_SUBREG [[DEF]], [[COPY5]], %subreg.dsub
  ; CHECK-NEXT:   [[COPY6:%[0-9]+]]:fpr64 = COPY [[COPY3]]
  ; CHECK-NEXT:   [[COPY7:%[0-9]+]]:fpr64 = COPY [[COPY4]]
  ; CHECK-NEXT:   [[DUPv2i32lane:%[0-9]+]]:fpr64 = DUPv2i32lane [[INSERT_SUBREG]], 0
  ; CHECK-NEXT:   [[DEF1:%[0-9]+]]:fpr128 = IMPLICIT_DEF
  ; CHECK-NEXT:   [[INSERT_SUBREG1:%[0-9]+]]:fpr128 = INSERT_SUBREG [[DEF1]], [[COPY]], %subreg.ssub
  ; CHECK-NEXT:   [[INSvi32lane:%[0-9]+]]:fpr128 = INSvi32lane [[INSERT_SUBREG]], 1, killed [[INSERT_SUBREG1]], 0
  ; CHECK-NEXT:   [[COPY8:%[0-9]+]]:fpr64 = COPY [[INSvi32lane]].dsub
  ; CHECK-NEXT:   STRDui killed [[COPY8]], [[COPY1]], 0 :: (store (s64) into %ir.ret2)
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1.for.cond:
  ; CHECK-NEXT:   [[FMULv2i32_indexed:%[0-9]+]]:fpr64 = FMULv2i32_indexed [[COPY7]], [[INSERT_SUBREG]], 0, implicit $fpcr
  ; CHECK-NEXT:   [[FADDv2f32_:%[0-9]+]]:fpr64 = FADDv2f32 killed [[FMULv2i32_indexed]], [[COPY6]], implicit $fpcr
  ; CHECK-NEXT:   STRDui killed [[FADDv2f32_]], [[COPY2]], 0 :: (store (s64) into %ir.ret, align 16)
  ; CHECK-NEXT:   B %bb.1
  bb.0.entry:
    liveins: $d0, $d1, $d2, $x0, $x1, $s3

    %6:fpr32 = COPY $s3
    %5:gpr64common = COPY $x1
    %4:gpr64common = COPY $x0
    %3:fpr64 = COPY $d2
    %2:fpr64 = COPY $d1
    %1:fpr64 = COPY $d0
    %10:fpr128 = IMPLICIT_DEF
    %9:fpr128 = INSERT_SUBREG %10, %1, %subreg.dsub
    %8:fpr64 = COPY %3
    %7:fpr64 = COPY %2
    %0:fpr64 = DUPv2i32lane %9, 0
    %12:fpr128 = IMPLICIT_DEF
    %11:fpr128 = INSERT_SUBREG %12, %6, %subreg.ssub
    %13:fpr128 = INSvi32lane killed %9, 1, killed %11, 0
    %14:fpr64 = COPY %13.dsub
    STRDui killed %14, %5, 0 :: (store (s64) into %ir.ret2)

  bb.1.for.cond:
    %15:fpr64 = FMULv2f32 %7, %0, implicit $fpcr
    %16:fpr64 = FADDv2f32 killed %15, %8, implicit $fpcr
    STRDui killed %16, %4, 0 :: (store (s64) into %ir.ret, align 16)
    B %bb.1

...
---
name:            extracopy
alignment:       16
tracksRegLiveness: true
registers:
  - { id: 0, class: fpr64 }
  - { id: 1, class: fpr64 }
  - { id: 2, class: fpr64 }
  - { id: 3, class: fpr64 }
  - { id: 4, class: gpr64common }
  - { id: 5, class: fpr64 }
  - { id: 6, class: fpr64 }
  - { id: 7, class: fpr128 }
  - { id: 8, class: fpr128 }
  - { id: 9, class: fpr64 }
  - { id: 10, class: fpr64 }
  - { id: 11, class: fpr64 }
liveins:
  - { reg: '$d0', virtual-reg: '%1' }
  - { reg: '$d1', virtual-reg: '%2' }
  - { reg: '$d2', virtual-reg: '%3' }
  - { reg: '$x0', virtual-reg: '%4' }
frameInfo:
  maxAlignment:    1
  maxCallFrameSize: 0
machineFunctionInfo: {}
body:             |
  ; CHECK-LABEL: name: extracopy
  ; CHECK: bb.0:
  ; CHECK-NEXT:   liveins: $d0, $d1, $d2, $x0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:gpr64common = COPY $x0
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:fpr64 = COPY $d2
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:fpr64 = COPY $d1
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:fpr64 = COPY $d0
  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:fpr128 = IMPLICIT_DEF
  ; CHECK-NEXT:   [[INSERT_SUBREG:%[0-9]+]]:fpr128 = INSERT_SUBREG [[DEF]], [[COPY3]], %subreg.dsub
  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:fpr64 = COPY [[COPY1]]
  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:fpr64 = COPY [[COPY2]]
  ; CHECK-NEXT:   [[DUPv2i32lane:%[0-9]+]]:fpr64 = DUPv2i32lane [[INSERT_SUBREG]], 0
  ; CHECK-NEXT:   [[COPY6:%[0-9]+]]:fpr64 = COPY [[DUPv2i32lane]]
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1:
  ; CHECK-NEXT:   [[FMULv2i32_indexed:%[0-9]+]]:fpr64 = FMULv2i32_indexed [[COPY5]], [[INSERT_SUBREG]], 0, implicit $fpcr
  ; CHECK-NEXT:   [[FADDv2f32_:%[0-9]+]]:fpr64 = FADDv2f32 killed [[FMULv2i32_indexed]], [[COPY4]], implicit $fpcr
  ; CHECK-NEXT:   STRDui killed [[FADDv2f32_]], [[COPY]], 0 :: (store (s64), align 16)
  ; CHECK-NEXT:   B %bb.1
  bb.0:
    liveins: $d0, $d1, $d2, $x0

    %4:gpr64common = COPY $x0
    %3:fpr64 = COPY $d2
    %2:fpr64 = COPY $d1
    %1:fpr64 = COPY $d0
    %8:fpr128 = IMPLICIT_DEF
    %7:fpr128 = INSERT_SUBREG %8, %1, %subreg.dsub
    %6:fpr64 = COPY %3
    %5:fpr64 = COPY %2
    %11:fpr64 = DUPv2i32lane killed %7, 0
    %0:fpr64 = COPY %11

  bb.1:
    %9:fpr64 = FMULv2f32 %5, %0, implicit $fpcr
    %10:fpr64 = FADDv2f32 killed %9, %6, implicit $fpcr
    STRDui killed %10, %4, 0 :: (store 8, align 16)
    B %bb.1

...